UEval: A Benchmark for Unified Multimodal Generation
What is UEval?
UEval comprises 1,000 expert-curated prompts that require both images and text in the model outputs, sourced from 8 diverse real-world domains.

Full-Leaderboard
view UEval problems
submit your results
Submit your results by opening an issue in our GitHub.
BibTeX
@article{li2026ueval,
title = {UEval: A Benchmark for Unified Multimodal Generation},
author = {Li, Bo and Yin, Yida and Chai, Wenhao and Fu, Xingyu and Liu, Zhuang},
journal = {arXiv preprint arXiv:2601.22155},
year = {2026}
}Website template modified from https://www.tbench.ai/.